My research interest is reinforcement learning with the emphasis on probabilistic and statistical methodology.
-
Harvard University
- Boston, USA
- https://sites.google.com/view/kesun
Highlights
- Pro
Pinned Loading
-
ARMADesign
ARMADesign PublicImplementation for "Optimal Treatment Allocation Strategies for A/B Testing in Partially Observable Time Series Experiments"
-
SinkhornDistRL
SinkhornDistRL PublicImplementation of 'Distributional Reinforcement Learning with Regularized Wasserstein Loss' (NeurIPS 2024)
Python 5
-
Papers-Of-Continual-RL
Papers-Of-Continual-RL PublicRelated papers for Continual Reinforcement Learning.
-
Papers-Of-DistributionalRL
Papers-Of-DistributionalRL PublicRelated papers for Distributional Reinforcement Learning (DistRL).
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.